Depth Pro
AppleDepth Pro is Apple's monocular depth model: from a single image it produces a metric depth map, with absolute scale, and estimates the camera's focal length without needing camera metadata. A multi-scale Vision Transformer built on DINOv2 encoders does the work, and the repository's model is a re-trained reference implementation close to, but not matching, the paper's. A Transformers-format checkpoint is also on the Hugging Face Hub.
Openness
2 high confidence- weights
- open (depth_pro.pt and the Transformers checkpoint on the Hub, ungated)
- data
- documented-not-released (the card lists the real and synthetic training datasets in a table; no mixture is released)
- code
- partial (inference, command-line and boundary-metric evaluation code; no training code)
- license
- Apple-AMLR (Apple Machine Learning Research Model license on the checkpoints; non-commercial research only. The repository code is under Apple's separate sample-code license)
The Depth Pro checkpoints carry Apple's research-model license, which limits use to non-commercial scientific research and excludes any commercial product or service. The repository code is under a separate permissive Apple license, but it covers inference and evaluation, not training.
- https://huggingface.co/api/models/apple/DepthPro recorded 2026-11-12
Hub record for apple/DepthPro: gated false, license apple-amlr, depth_pro.pt and LICENSE.
- https://huggingface.co/api/models/apple/DepthPro-hf recorded 2026-11-12
Hub record for apple/DepthPro-hf: gated false, license apple-amlr, model.safetensors.
- https://huggingface.co/apple/DepthPro-hf/raw/main/README.md recorded 2026-11-12
DepthPro-hf card: "The DepthPro model was trained on the following datasets", given as a table image; no dataset release.
- https://huggingface.co/apple/DepthPro/raw/main/LICENSE recorded 2026-11-12
Apple Machine Learning Research Model license: use is granted "exclusively for Research Purposes", which "does not include any commercial exploitation, product development or use in any commercial product or service".
- https://raw.githubusercontent.com/apple-aiml-research/ml-depth-pro/main/LICENSE recorded 2026-11-12
Repository LICENSE: Apple's sample-code license, granting use, reproduction, modification and redistribution of the Apple Software with or without modifications.
- https://raw.githubusercontent.com/apple-aiml-research/ml-depth-pro/main/README.md recorded 2026-11-12
README: install, checkpoint download, command-line and Python inference, and boundary-metric evaluation; "The model in this repository is a reference implementation, which has been re-trained"; no training instructions.
Adoption
2 high confidenceHugging Face downloads over the trailing 30 days for the two declared checkpoints, almost all of them for the Transformers version.
- https://huggingface.co/api/models?author=apple&search=depth&limit=100&expand[]=downloads&expand[]=cardData&expand[]=gated recorded 2026-11-12
apple/DepthPro-hf 54,290 and apple/DepthPro 5,726 downloads in the trailing 30 days (60,016 together).
Capability
4 high confidenceDepth Pro returns a metric depth map for any image the user supplies, without training, as Depth Anything does. It works from one image at a time, where Depth Anything 3 also takes several views and estimates camera pose.
- https://raw.githubusercontent.com/apple-aiml-research/ml-depth-pro/main/README.md recorded 2026-11-12
README: "We present a foundation model for zero-shot metric monocular depth estimation"; "producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU"; prediction returns depth in meters and focallength_px.
Verified 2026-11-12